01The booth asks for two angles
From 0 to about 3.54 seconds the camera sees the rapper in side profile at a hanging silver condenser mic, rubbing a forearm. From 3.54 to 12.46 seconds one continuous shot moves closer and more frontal, looking at the rapper from behind the mic. A clear, well-lit photo with the face slightly turned serves both, because it shows the nose, jaw and ear line as well as both eyes. A strict front-facing passport-style shot suits the second angle but gives the profile less to go on.
02Plan for the microphone covering your face
In the long frontal shot the mic sits between the camera and the rapper and covers part of the face. Whatever stays visible beside it has to identify you: the eye on the near side, the cheek, hairline and jaw. Choose a photo where those are sharp and not shaded by a cap brim, hair or a hand. Large items around the mouth, such as a face mask or a mic in your own photo, add confusion near the area the booth mic already hides.
03Your hands and sleeves are on screen
The booth includes a two-finger sign around 4.5 seconds, a finger pointed toward the mic between about 6 and 7.5 seconds, and arms spread wide between about 10 and 12 seconds. Because the outfit comes from your photo, the sleeves, wrists and anything worn on them are visible in these gestures. A photo that shows your arms or at least your top and sleeves gives the generation real information. A tight face crop leaves it to guess what your arms look like.
04A verse that never pauses
A machine transcript of the reel shows the rap running almost continuously from 0.08 seconds to about 20.6 seconds. There are no long gaps to hide a mismatch, so mouth timing is the first thing to review. Watch the booth with sound at normal speed, then pick three moments: one in the side profile, one during the pointed-finger gesture, and one just before the cut to the stage at 12.46 seconds. At each one, check that the mouth is open on syllables and closes between phrases rather than moving on its own rhythm.
05Nine seconds without a cut
The frontal booth shot runs from 3.54 to 12.46 seconds as one continuous take with a gentle handheld drift. There is no cut to hide a change, so anything that shifts inside it is visible: a hairstyle that grows or shortens, a top that changes colour, an accessory that appears mid-verse. Watch the shot once looking only at the outfit and hair. If something changes, note the time; that is a real continuity issue worth reviewing before you post.
06Before you submit
Use a photo with one person in it, of yourself or of someone who has agreed to appear. Wear the outfit you want in every shot with you in it, since it follows you from the booth into the montage. Pick 480p, 720p or 1080p, read the quote, and only then generate. This page does not report any tested success rate; it explains what the booth section asks of your photo.
